®®®® SIIA Público

Título del libro: Naacl Hlt 2018 - International Workshop On Semantic Evaluation, Semeval 2018 - Proceedings Of The 12th Workshop
Título del capítulo: UNAM at SemEval-2018 Task 10: Unsupervised Semantic Discriminative Attribute Identification in Neural Word Embedding Cones

Autores UNAM:
IGNACIO ARROYO FERNANDEZ;
Autores externos:
Idioma:
Año de publicación:
2018
Palabras clave:

Embeddings; Fuzzy logic; Mathematical operators; Semantics; Decision functions; Embeddings; Features sets; Fuzzy intersections; On state; Set operation; State of the art; T - Norm; Unsupervised method; Vector operations; Cones

Resumen:

In this paper we report an unsupervised method aimed to identify whether an attribute is discriminative for two words (which are treated as concepts, in our particular case). To this end, we use geometrically inspired vector operations underlying unsupervised decision functions. These decision functions operate on state-of-the-art neural word embeddings of the attribute and the concepts. The main idea can be described as follows: if attribute q discriminates concept a from concept b, then q is excluded from the feature set shared by these two concepts: the intersection. That is, the membership q ? (a n b) does not hold. As a, b, q are represented with neural word embeddings, we tested vector operations allowing us to measure membership, i.e. fuzzy set operations (t-norm, for fuzzy intersection, and t-conorm, for fuzzy union) and the similarity between q and the convex cone described by a and b. © 2018 Association for Computational Linguistics

Entidades citadas de la UNAM:
Fuente:


ISBN:
9781948087209
Editorial:
Association for Computational Linguistics (ACL)

Tipo de producto:
Conference Paper